Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 371
    Prev
    Next
    INDEX
    Explanations

    discussion of legal actions, investigations, and consequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.19
    0.9%
    608
    +0.16
    0.8%
    362
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.28
    608
    +0.16
    0.26
    616
    +0.16
    0.15
    Negative Logits
    thens
    -0.81
    soever
    -0.77
    ateurs
    -0.75
    ometers
    -0.73
    apps
    -0.70
    rete
    -0.70
    rooms
    -0.69
    acers
    -0.68
    brates
    -0.66
     whichever
    -0.66
    POSITIVE LOGITS
     lack
    1.49
     inability
    1.38
     shortcomings
    1.33
     plight
    1.30
     tendency
    1.30
     absence
    1.27
     reluctance
    1.27
     impending
    1.26
     resurgence
    1.22
     importance
    1.21
    Activations Density 6.371%

    No Known Activations